Ice crack detection robot and detection method

Abstract

The present invention relates to the field of mechanical arm control technology, and specifically proposes an ice crack detection robot and detection method, the device comprising: a shell, a ski, a collection device, a first mechanical arm, a second mechanical arm, a pressure mechanical arm, a power unit and a controller. The controller is fixedly arranged inside the shell, and is electrically connected to the collection device, the first mechanical arm, the second mechanical arm, the pressure mechanical arm and the power unit, respectively, for controlling the operation of the robot. The present invention integrates image acquisition, radar detection, purging and deformation force acquisition, realizes real-time acquisition of ice crack image data and echo amplitude data, and performs real-time analysis and judgment, thereby ensuring the accuracy of the detection data, and being able to timely discover the existence of ice cracks and assess the risk level.

Description

Technical Field

[0001] The present invention relates to the technical field of robot arm control, and in particular to an ice crack detection robot and a detection method. Background Art

[0002] When researchers conduct expeditions in polar regions, they often need to use snowmobiles and other means of transportation to transport goods on the ice. Due to the movement of glaciers, cracks of various sizes often form on the ice. Due to the harsh climate in polar regions, snow often covers the cracks, making it difficult to detect and measure these cracks through satellite images or visual observation, which brings difficulties to the transportation of sea ice cargo. Therefore, monitoring ice cracks is crucial during polar expeditions.

[0003] At present, sea ice observation mainly relies on satellite remote sensing, ship-borne or airborne radar, electromagnetic induction, laser ranging and ship-borne sonar equipment, which can detect the thickness of medium and large-scale sea ice. However, although satellite images have a wide coverage, their accuracy is limited and they cannot accurately measure the location of ice cracks in the direction of travel. Manual detection of ice cracks requires personnel to walk on the ice and use tools such as snow picks for detection and measurement. Although this method is reliable, it has safety risks.

[0004] Therefore, it is necessary to design an ice crack detection robot and detection method to solve the problems existing in current technology. Summary of the invention

[0005] In view of this, the present invention proposes an ice crack detection robot and a detection method, aiming to solve the problems existing in the current ice crack detection technology, such as limited detection accuracy, inability to achieve accurate detection in a small range, and potential safety hazards caused by relying on manual detection.

[0006] The present invention provides an ice crack detection robot, comprising:

[0007] case;

[0008] A ski board, fixedly arranged below the housing, wherein at least one ski board is arranged;

[0009] A collection device, fixedly arranged in front of the shell, and used for collecting image data in front of the detection robot;

[0010] a first mechanical arm, a radar detector being arranged at the head thereof, the first mechanical arm being rotatably arranged above the shell, and the first mechanical arm being used for detecting ice layers;

[0011] a second mechanical arm, wherein a blowing fan is disposed at the head thereof, the second mechanical arm is rotatably disposed above the housing and located at one side of the first mechanical arm, and the second mechanical arm is used for blowing away the ice layer;

[0012] A pressure mechanical arm is arranged in front of the shell and is located on one side of the collection device, and is used to apply pressure to the detection position and collect the deformation force of the ice layer;

[0013] A power device, fixedly arranged at the rear of the housing, and driving the robot to operate;

[0014] A controller is fixedly disposed inside the housing and is electrically connected to the collection device, the first mechanical arm, the second mechanical arm, the pressure mechanical arm and the power device, respectively. The controller is used to:

[0015] Collecting detection path information, obtaining a total detection length, and determining an interval time of detection by the first mechanical arm according to the total detection length;

[0016] Before controlling the first robotic arm to perform detection, controlling the acquisition device to acquire image data of the ice layer in front, analyzing the image data to obtain whether there is floating snow on the surface of the ice layer; when it is determined that there is floating snow on the surface of the ice layer, obtaining the area of ​​floating snow, and controlling the second robotic arm to blow away the ice layer according to the area of ​​floating snow;

[0017] After determining whether to purge the ice layer, controlling the first mechanical arm to detect the current position, collecting echo amplitude data, and determining whether there is an ice crack at the current position according to the echo amplitude data;

[0018] When it is determined that there is an ice crack at the current position, the echo arrival time is collected and the pressure robot arm is controlled to apply pressure to the detection position to collect the deformation force of the ice layer. The risk level of the current position is obtained based on the echo amplitude data, the echo arrival time and the deformation force.

[0019] Furthermore, when the controller determines the interval time of the first mechanical arm detection according to the total detection length, it includes:

[0020] The controller compares the total detection length L with a first preset total detection length L1 and a second preset total detection length L2 respectively, L1<L2, and determines the detection interval time of the first robot arm according to the comparison result;

[0021] When L≤L1, the controller determines that the detection interval of the first mechanical arm is a first preset interval T1;

[0022] When L1<L≤L2, the controller determines that the detection interval of the first mechanical arm is a second preset interval T2;

[0023] When L2<L, the controller determines that the detection interval of the first robot arm is a third preset interval T3;

[0024] Among them, T1<T2<T3.

[0025] Furthermore, when the controller analyzes the image data to obtain whether there is floating snow on the surface of the ice layer, it includes:

[0026] Preprocessing the image data, wherein the preprocessing includes denoising, graying, and edge detection;

[0027] Extracting texture information from the image, comparing the texture information with ice surface texture information, and determining whether there is floating snow on the ice surface based on the comparison result;

[0028] When the texture information does not match the ice surface texture information, it is determined that floating snow exists on the surface of the ice layer, and the floating snow area M is obtained based on the edge detection.

[0029] Furthermore, when the controller controls the second mechanical arm to clear the ice layer according to the floating snow area, it includes:

[0030] The controller compares the floating snow area M with the first preset floating snow area M1 and the second preset floating snow area M2 respectively, M1<M2, and determines the blowing speed of the second mechanical arm when blowing the ice layer according to the comparison result;

[0031] When M≤M1, the controller determines that the blowing speed of the second mechanical arm when blowing the ice layer is the first preset speed S1;

[0032] When M1<M≤M2, the controller determines that the blowing speed of the second mechanical arm when blowing the ice layer is a second preset speed S2;

[0033] When M2<M, the controller determines that the blowing speed of the second mechanical arm when blowing the ice layer is a third preset speed S3;

[0034] Among them, S1<S2<S3.

[0035] Further, after determining that the detection interval of the first mechanical arm is the i-th preset interval time Ti, i=1, 2, 3, the controller determines whether there is an ice crack at the current position according to the echo amplitude data, including:

[0036] The controller compares the echo amplitude data F with a preset echo amplitude threshold Fmin, and determines whether there is an ice crack at the current position according to the comparison result;

[0037] When F<Fmin, the controller determines that there is no ice crack at the current position, but there are ice cracks around the current position, and obtains the amplitude difference ΔF, ΔF=Fmin-F, and adjusts the detection interval time Ti of the first mechanical arm according to the amplitude difference ΔF;

[0038] When F=Fmin, the controller determines that there is no ice crack at the current position, and controls the first robotic arm to continue detecting at an interval time Ti;

[0039] When F>Fmin, the controller determines that there is an ice crack at the current position, collects the echo arrival time Q, and determines the depth of the ice crack according to the echo arrival time Q.

[0040] Further, when the controller adjusts the detection interval Ti of the first robot arm according to the amplitude difference ΔF, it includes:

[0041] The controller compares the amplitude difference ΔF with a first preset amplitude difference ΔF1 and a second preset amplitude difference ΔF2 respectively, ΔF1<ΔF2, and determines a time adjustment coefficient according to the comparison result to adjust the interval time Ti;

[0042] When ΔF≤ΔF1, a first preset time adjustment coefficient A1 is determined to adjust the interval time Ti, and the operation continues with the adjusted interval time Ti*A1;

[0043] When ΔF1<ΔF≤ΔF2, determine the second preset time adjustment coefficient A2 to adjust the interval time Ti, and continue to run with the adjusted interval time Ti*A2;

[0044] When ΔF2<ΔF, determine the third preset time adjustment coefficient A3 to adjust the interval time Ti, and continue to run with the adjusted interval time Ti*A3;

[0045] Among them, 0<A1<A2<A3<1.

[0046] Further, when the controller determines the ice crack depth according to the echo arrival time Q, it includes:

[0047] The controller compares the echo arrival time Q with a first preset echo arrival time Q1 and a second preset echo arrival time Q2 respectively, Q1<Q2, and determines the ice crack depth according to the comparison result;

[0048] When Q≤Q1, the controller determines that the ice crack depth is a first preset depth E1;

[0049] When Q1<Q≤Q2, the controller determines that the ice crack depth is a second preset depth E2;

[0050] When Q2<Q, the controller determines that the ice crack depth is a third preset depth E3;

[0051] Among them, 0<E1<E2<E3.

[0052] Furthermore, when the controller obtains the risk level of the current position according to the echo amplitude data, the echo arrival time and the deformation force, it includes:

[0053] The controller obtains an echo amplitude overflow value Fy, where Fy=F-Fmin, and compares the echo amplitude overflow value Fy with a first preset overflow value Fy1 and a second preset overflow value Fy2, respectively, where Fy1<Fy2, and determines the ice crack width according to the comparison result;

[0054] When Fy≤Fy1, the controller determines that the ice crack width is a third preset width K3;

[0055] When Fy1<Fy≤Fy2, the controller determines that the ice crack width is a second preset width K2;

[0056] When Fy2<Fy, the controller determines that the ice crack width is a first preset width K1;

[0057] Among them, 0<K1<K2<K3.

[0058] Further, when the controller determines that the ice crack depth is the i-th preset depth Ei and the ice crack width is the n-th preset width Kn, i=1, 2, 3, n=1, 2, 3, the controller obtains the risk level of the current position according to the echo amplitude data, the echo arrival time and the deformation force, and further includes:

[0059] The controller obtains the current position risk coefficient P according to the ice crack depth Ei, the ice crack width Kn and the deformation force N. The risk coefficient P is calculated by the following formula:

[0060] P = Ei*a + Kn*bN*c;

[0061] Wherein, a, b, c represent weight coefficients, a+b+c=1;

[0062] The controller compares the risk coefficient P with a first preset risk coefficient P1 and a second preset risk coefficient P2 respectively, P1<P2, and obtains the risk level of the current position according to the comparison result;

[0063] When P≤P1, the risk level of the current location is determined to be the third preset risk level D3;

[0064] When P1<P≤P2, the risk level of the current location is determined to be the second preset risk level D2;

[0065] When P2<P, the risk level of the current location is determined to be the first preset risk level D1;

[0066] The first preset risk level D1 indicates that the danger level of ice cracks is higher than that of the second preset risk level D2, and the second preset risk level D2 indicates that the danger level of ice cracks is higher than that of the third preset risk level D3.

[0067] Compared with the prior art, the beneficial effect of the present invention is that by using robots to replace manual ice crack detection, the working risk of personnel in the harsh polar environment is effectively reduced, and the potential safety hazards caused by direct contact with the ice surface are avoided. The existence of the pressure mechanical arm enables the robot to apply pressure in time when the ice crack is found, collect the deformation force of the ice layer, realize the force analysis of the ice crack, and is conducive to fully understanding the bearing capacity of the ice crack. The robot automatically performs the ice crack detection task, is not restricted by the polar environment, can continue to work under harsh weather conditions, and improves the efficiency and coverage of ice crack detection. The first mechanical arm is equipped with a radar detector, which can quickly and accurately detect the ice layer, while the second mechanical arm can remove the floating snow on the ice surface through the purge fan to ensure the accuracy and reliability of the detection. It integrates multiple functional modules, including image acquisition, radar detection, purge and deformation force acquisition, etc., to ensure the accuracy of the detection data, realize the real-time collection of ice crack image data and echo amplitude data, and perform real-time analysis and judgment. The controller can timely detect the existence of ice cracks and evaluate the risk level, providing timely safety protection for cargo transportation on the ice surface.

[0068] On the other hand, the present application also provides an ice crack detection method, which is applied to the above-mentioned ice crack detection robot, comprising:

[0069] Collecting detection path information, obtaining a total detection length, and determining an interval time of detection by the first robotic arm according to the total detection length;

[0070] Before detection, the acquisition device is controlled to acquire image data of the ice layer in front, and the image data is analyzed to obtain whether there is floating snow on the surface of the ice layer; when it is determined that there is floating snow on the surface of the ice layer, the floating snow area is obtained, and the second mechanical arm is controlled to blow the ice layer according to the floating snow area;

[0071] After determining whether to purge the ice layer, controlling the first mechanical arm to detect the current position, collecting echo amplitude data, and determining whether there is an ice crack at the current position according to the echo amplitude data;

[0072] When it is determined that there is an ice crack at the current position, the echo arrival time is collected and the pressure robot arm is controlled to apply pressure to the detection position to collect the deformation force of the ice layer. The risk level of the current position is obtained based on the echo amplitude data, the echo arrival time and the deformation force.

[0073] It can be understood that the ice crack detection robot and detection method provided in the present application have the same beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0075] Figure 1 A schematic diagram of the structure of an ice crack detection robot provided by an embodiment of the present invention;

[0076] Figure 2 A front view of an ice crack detection robot provided by an embodiment of the present invention;

[0077] Figure 3 A flow chart of an ice crack detection method provided in an embodiment of the present invention.

[0078] Among them, 110, shell; 120, skis; 130, collection device; 140, first robotic arm; 141, radar detector; 150, second robotic arm; 151, purge fan; 160, pressure robotic arm; 170, power unit; 180, controller. DETAILED DESCRIPTION

[0079] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0080] See also Figure 1-2 As shown, this embodiment provides an ice crack detection robot, comprising:

[0081] The housing 110, the ski 120, the collection device 130, the first mechanical arm 140, the second mechanical arm 150, the pressure mechanical arm 160, the power device 170 and the controller 180, wherein:

[0082] The housing 110 is the external structural frame of the entire ice crevasse detection robot, which is used to support and protect the various functional modules of the robot. Various fixing devices and interfaces are pre-designed on the housing 110 for fixing and installing various functional modules, such as the skis 120, the collection device 130, the robotic arm, etc. The housing 110 has waterproof and dustproof functions, which can effectively prevent external impurities such as water and dust from entering the robot, and protect the internal controller 180 from damage.

[0083] The skis 120 are fixedly arranged under the shell 110 for traveling on ice. The number of the skis 120 can be set as needed, and at least one is set to ensure the stability and balance of the robot.

[0084] The acquisition device 130 is fixedly arranged in front of the shell 110. The acquisition device 130 is used to collect image data in front of the detection robot. It uses a camera or other image sensors and is equipped with an image processing system to achieve the acquisition, processing and analysis of ice surface images.

[0085] A radar detector 141 is disposed at the head of the first mechanical arm 140 . The first mechanical arm 140 is rotatably disposed above the shell 110 and is driven by a motor to achieve rotation. The first mechanical arm 140 is used to detect ice layers.

[0086] A blowing fan 151 is disposed at the head of the second robotic arm 150 . The second robotic arm 150 is rotatably disposed above the shell 110 , driven by a motor to rotate, and is located on one side of the first robotic arm 140 . The second robotic arm 150 is used to blow away the ice layer.

[0087] The pressure mechanical arm 160 is arranged in front of the housing 110 and is located on one side of the collection device 130. The pressure mechanical arm 160 is used to apply pressure to the detection position and collect the deformation force of the ice layer. The pressure on the detection position is applied by a hydraulic system, and a sensor is provided to collect deformation force data in real time. The pressure mechanical arm 160 can be extended to apply pressure to the ice layer when in use by setting a telescopic device, and retracted when not in use.

[0088] The power device 170 is fixedly arranged at the rear of the shell 110 . The power device 170 drives the robot to operate, preferably driven by a fan. The robot can be equipped with a power supply to provide electrical energy to the power device 170 and the control device, or photovoltaic panels can be arranged around the shell 110 .

[0089] The controller 180 is fixedly disposed inside the housing 110 and is electrically connected to the collection device 130, the first mechanical arm 140, the second mechanical arm 150, the pressure mechanical arm 160 and the power device 170 respectively. The controller 180 is used to:

[0090] The detection path information is collected to obtain the total detection length, and the detection interval time of the first mechanical arm 140 is determined according to the total detection length.

[0091] Before controlling the first mechanical arm 140 to detect, the acquisition device 130 is controlled to collect image data of the ice layer in front, and the image data is analyzed to obtain whether there is floating snow on the surface of the ice layer. When it is determined that there is floating snow on the surface of the ice layer, the floating snow area is obtained, and the second mechanical arm 150 is controlled to blow away the ice layer according to the floating snow area.

[0092] After determining whether to clear the ice layer, the first mechanical arm 140 is controlled to detect the current position, collect echo amplitude data, and determine whether there is an ice crack at the current position based on the echo amplitude data.

[0093] When it is determined that there is an ice crack at the current position, the echo arrival time is collected and the pressure robot 160 is controlled to apply pressure to the detection position to collect the deformation force of the ice layer. The risk level of the current position is obtained based on the echo amplitude data, echo arrival time and deformation force.

[0094] It can be understood that by integrating image acquisition, radar detection, blowing and deformation force acquisition, etc., a comprehensive detection capability of ice cracks is achieved. The acquisition device 130 can obtain image data of the ice layer in front, the first mechanical arm 140 is equipped with a radar detector 141 for detection, the second mechanical arm 150 is used to blow floating snow, and the pressure mechanical arm 160 collects deformation force data. By comprehensively utilizing this information, the position and size of the ice cracks can be accurately and comprehensively detected. Through the coordinated control of each functional module by the controller 180, the functions of collecting detection path information, identifying floating snow, detecting ice cracks and collecting deformation force can be realized. Once an ice crack is found, the echo amplitude and arrival time can be collected in time, and the pressure mechanical arm 160 can be controlled in real time to apply pressure and collect deformation force data to obtain the risk level of the current position. The power device 170 provides the power drive of the robot, which can realize the autonomous operation of the robot. By controlling the running trajectory and speed of the robot by the controller 180, the precise control of the detection path can be realized, ensuring that the robot can detect ice cracks according to the predetermined path, and improving the detection efficiency and accuracy. The provision of the skis 120 enables the robot to stably travel on the ice surface, thereby ensuring the stability and balance of the robot during operation.

[0095] In some embodiments of the present application, when the controller 180 determines the interval time of detection of the first robot arm 140 based on the total detection length, it includes: the controller 180 compares the total detection length L with the preset first preset detection total length L1 and the second preset detection total length L2, L1<L2, and determines the interval time of detection of the first robot arm 140 based on the comparison result.

[0096] Specifically, when L≤L1, the controller 180 determines that the detection interval of the first robot arm 140 is the first preset interval T1. When L1<L≤L2, the controller 180 determines that the detection interval of the first robot arm 140 is the second preset interval T2. When L2<L, the controller 180 determines that the detection interval of the first robot arm 140 is the third preset interval T3. Wherein, T1<T2<T3.

[0097] It is understandable that, depending on the total length of the detection, different interval times can be used to achieve effective utilization and conservation of resources. When the total length of the detection is short, the interval time can be relatively short to ensure more intensive detection of the ice layer, thereby improving the accuracy of the detection. When the total length of the detection is long, the interval time can be appropriately extended to reduce energy consumption and equipment wear, thereby achieving the purpose of saving resources. When the total length of the detection changes, the controller 180 can dynamically adjust according to the preset interval time scheme to ensure that the best detection effect can be achieved in different situations, thereby improving the robot's response ability and adaptability.

[0098] In some embodiments of the present application, when the controller 180 analyzes the image data to obtain whether there is floating snow on the ice surface, it includes: preprocessing the image data, and the preprocessing includes denoising, graying, and edge detection. Extracting texture information in the image, comparing the texture information with the ice surface texture information, and determining whether there is floating snow on the ice surface based on the comparison result. When the texture information does not match the ice surface texture information, it is determined that there is floating snow on the ice surface, and the floating snow area M is obtained based on edge detection.

[0099] It is understandable that to extract texture information from an image, texture feature descriptors or texture analysis algorithms, such as Local Binary Patterns (LBP), Gray Level Co-occurrence Matrix (GLCM), etc., can be used to extract texture features from the image. According to the known ice surface texture information, the texture information extracted from the image is compared with the ice surface texture information. Classification and identification are performed by calculating the similarity between texture features. When the texture information extracted from the image does not match the ice surface texture information, that is, the similarity of the texture information is lower than the set threshold, it can be determined that there is floating snow on the surface of the ice layer. In the case of determining that there is floating snow on the surface of the ice layer, the area M of the floating snow is obtained by calculating the number of edge pixels or using an image segmentation algorithm to segment the floating snow area, and calculating the number of pixels in the floating snow area.

[0100] In some embodiments of the present application, when the controller 180 controls the second robotic arm 150 to blow the ice layer according to the floating snow area, it includes: the controller 180 compares the floating snow area M with the preset first preset floating snow area M1 and the second preset floating snow area M2, respectively, M1<M2, and determines the blowing speed of the blowing motor when the second robotic arm 150 blows the ice layer according to the comparison result.

[0101] Specifically, when M≤M1, the controller 180 determines that the blowing speed of the second mechanical arm 150 when blowing the ice layer is the first preset speed S1. When M1<M≤M2, the controller 180 determines that the blowing speed of the second mechanical arm 150 when blowing the ice layer is the second preset speed S2. When M2<M, the controller 180 determines that the blowing speed of the second mechanical arm 150 when blowing the ice layer is the third preset speed S3. Wherein, S1<S2<S3.

[0102] It is understandable that by determining the blowing speed according to the floating snow area, the power and resources of the blowing robot arm can be effectively utilized. When the floating snow area is small, using a lower blowing speed saves energy and reduces the wear of the robot arm, thereby improving resource utilization efficiency. Determining different blowing speeds according to the floating snow area can make the robot more adaptable and flexible in different ice surface conditions. When the floating snow area is small, using a lower blowing speed can clean the ice surface more finely and improve the cleaning efficiency; when the floating snow area is large, using a higher blowing speed can quickly clean a large area of ​​floating snow and improve work efficiency.

[0103] In some embodiments of the present application, after determining that the interval time detected by the first robotic arm 140 is the i-th preset interval time Ti, i=1, 2, 3, the controller 180 determines whether there is an ice crack at the current position based on the echo amplitude data, including: the controller 180 compares the echo amplitude data F with the preset echo amplitude threshold Fmin, and determines whether there is an ice crack at the current position based on the comparison result.

[0104] Specifically, when F<Fmin, the controller 180 determines that there is no ice crack at the current position, but there are ice cracks around the current position, and obtains the amplitude difference ΔF, ΔF=Fmin-F, and adjusts the detection interval Ti of the first mechanical arm 140 according to the amplitude difference ΔF. When F=Fmin, the controller 180 determines that there is no ice crack at the current position, and controls the first mechanical arm 140 to continue detection at the interval Ti. When F>Fmin, the controller 180 determines that there is an ice crack at the current position, collects the echo arrival time Q, and determines the depth of the ice crack according to the echo arrival time Q.

[0105] It is understandable that when the radar signal encounters an ice crack, part of the signal will be reflected or diffracted, causing the received echo amplitude to change. Ice cracks are a large inhomogeneity. Compared with the flat part of the ice surface, the signal reflection at the crack will be stronger, and a larger echo amplitude will be observed at the crack. This is because the crack is an area with a higher dielectric constant relative to the air. When the radar wave encounters a crack, part of the energy will be reflected back, and the interface with different dielectric constants will lead to an enhancement of the reflected signal. The larger the crack, the larger its surface area is, and the more energy can be reflected back, resulting in an increase in the echo amplitude. In the absence of cracks, the echo amplitude on the ice surface generally does not change significantly, because the propagation path of the radar wave on the ice layer is relatively uniform and will not be greatly disturbed or blocked. When F<Fmin, although the echo amplitude data at the current position does not meet the characteristics of the ice crack, the presence of ice cracks around it causes the sound wave to leak out, causing the echo amplitude to decrease. Therefore, according to the situation that the echo amplitude data is lower than the threshold, it is determined that there may be undetected ice cracks around the current position.

[0106] In some embodiments of the present application, when the controller 180 adjusts the interval time Ti detected by the first robot arm 140 according to the amplitude difference ΔF, it includes: the controller 180 compares the amplitude difference ΔF with the first preset amplitude difference ΔF1 and the second preset amplitude difference ΔF2 respectively, ΔF1<ΔF2, and determines the time adjustment coefficient according to the comparison result to adjust the interval time Ti.

[0107] Specifically, when ΔF≤ΔF1, the first preset time adjustment coefficient A1 is determined to adjust the interval time Ti, and the operation continues with the adjusted interval time Ti*A1. When ΔF1<ΔF≤ΔF2, the second preset time adjustment coefficient A2 is determined to adjust the interval time Ti, and the operation continues with the adjusted interval time Ti*A2. When ΔF2<ΔF, the third preset time adjustment coefficient A3 is determined to adjust the interval time Ti, and the operation continues with the adjusted interval time Ti*A3. Among them, 0<A1<A2<A3<1.

[0108] It is understandable that adjusting the interval time can make the robot detect more frequently around the ice cracks, thereby enhancing the detection sensitivity of the ice cracks. By monitoring and adjusting the amplitude difference, the existence and location of the ice cracks can be determined more accurately. When there are ice cracks around, adjusting the interval time can make the robot detect more frequently, reducing the possibility of missing the ice cracks and improving the comprehensiveness and accuracy of the detection.

[0109] In some embodiments of the present application, when the controller 180 determines the depth of the ice crack based on the echo arrival time Q, it includes: the controller 180 compares the echo arrival time Q with the preset first preset echo arrival time Q1 and the second preset echo arrival time Q2, respectively, Q1<Q2, and determines the depth of the ice crack based on the comparison result.

[0110] Specifically, when Q≤Q1, the controller 180 determines the ice crack depth to be the first preset depth E1. When Q1<Q≤Q2, the controller 180 determines the ice crack depth to be the second preset depth E2. When Q2<Q, the controller 180 determines the ice crack depth to be the third preset depth E3. Wherein, 0<E1<E2<E3.

[0111] In some embodiments of the present application, when the controller 180 obtains the risk level of the current position based on the echo amplitude data, the echo arrival time and the deformation force, it includes: the controller 180 obtains the echo amplitude overflow value Fy, Fy=F-Fmin, the controller 180 compares the echo amplitude overflow value Fy with the pre-set first preset overflow value Fy1 and the second preset overflow value Fy2, Fy1<Fy2, and determines the ice crack width according to the comparison result.

[0112] Specifically, when Fy≤Fy1, the controller 180 determines the ice crack width to be the third preset width K3. When Fy1<Fy≤Fy2, the controller 180 determines the ice crack width to be the second preset width K2. When Fy2<Fy, the controller 180 determines the ice crack width to be the first preset width K1. Wherein, 0<K1<K2<K3.

[0113] In some embodiments of the present application, when the controller 180 determines that the ice crack depth is the i-th preset depth Ei and the ice crack width is the n-th preset width Kn, i=1, 2, 3, n=1, 2, 3, and the controller 180 obtains the risk level of the current position based on the echo amplitude data, the echo arrival time and the deformation force, it also includes: the controller 180 obtains the risk coefficient P of the current position based on the ice crack depth Ei, the ice crack width Kn and the deformation force N, and the risk coefficient P is calculated by the following formula.

[0114] P=Ei*a+Kn*bN*c.

[0115] Wherein, a, b, c represent weight coefficients, and a+b+c=1.

[0116] Specifically, the controller 180 compares the risk coefficient P with a first preset risk coefficient P1 and a second preset risk coefficient P2, respectively, P1<P2, and obtains the risk level of the current location according to the comparison result.

[0117] Specifically, when P≤P1, the risk level of the current location is determined to be the third preset risk level D3. When P1<P≤P2, the risk level of the current location is determined to be the second preset risk level D2. When P2<P, the risk level of the current location is determined to be the first preset risk level D1. Among them, the first preset risk level D1 indicates that the danger level of the ice crack is higher than the second preset risk level D2, and the second preset risk level D2 indicates that the danger level of the ice crack is higher than the third preset risk level D3.

[0118] It is understandable that because sound waves are obstructed and scattered by cracks during propagation, part of the sound waves are reflected back to form echoes. When the width of the crack is larger, the echo amplitude will be smaller than that of a narrow crack. When a sound wave encounters an ice crack, an echo will be generated and returned. The difference between the time the detector receives the echo and the time the sound wave is emitted is the echo arrival time. Since the propagation speed of sound waves in different media is known, the distance the sound wave propagates in the ice layer can be inferred based on the echo arrival time, thereby determining the depth of the crack. If the crack is deeper, the sound wave takes longer to return, so the echo arrival time will be relatively delayed; on the contrary, if the crack is shallow, the time it takes for the sound wave to return will be relatively short. The risk factor P is proportional to the width and depth of the ice crack, and inversely proportional to the deformation force.

[0119] The operation process of the device in this application is:

[0120] The controller 180 obtains the detection task, identifies the detection route and collects the total detection length, sets the detection interval time according to the total detection length, and after determining the detection interval time, the power device 170 drives the robot to travel along the detection route. After the set detection interval time has passed, the controller 180 controls the power device 170 to stop, and controls the acquisition device 130 to collect images of the position in front of the robot. The acquisition device 130 can also be controlled to be always open. When no detection is performed, the robot avoids obstacles based on image acquisition. Whether there is floating snow on the ice layer is determined based on the image acquisition information. When there is floating snow, the second mechanical arm 150 is controlled to move downward and the purge fan 151 is turned on to purge the surface of the ice layer. After the purge is completed, the controller 180 controls the second mechanical arm 150 to move upward until it is reset. After the second robotic arm 150 is reset, the controller 180 controls the first robotic arm 140 to move downward, moves the radar detector 141 to above the detection position, turns on the radar detector 141 and collects echo amplitude data, and determines whether there is an ice crack at the detection position based on the echo amplitude data. When an ice crack exists, the controller 180 collects the echo arrival time and controls the pressure robotic arm 160 to extend. The pressure device at the head of the pressure robotic arm 160 applies pressure to the ice surface at the detection position, and records the pressure value when the ice surface is deformed. The controller 180 performs risk assessment based on the echo amplitude data, echo arrival time and ice surface deformation force.

[0121] In the above embodiment, by using robots to replace manual ice crack detection, the working risk of personnel in the harsh polar environment is effectively reduced, and the potential safety hazards caused by direct contact with the ice surface are avoided. The existence of the pressure mechanical arm enables the robot to apply pressure in time when the ice crack is found, collect the deformation force of the ice layer, realize the force analysis of the ice crack, and is conducive to fully understanding the bearing capacity of the ice crack. The robot automatically performs the ice crack detection task, is not restricted by the polar environment, can continue to work under harsh weather conditions, and improves the efficiency and coverage of ice crack detection. The first mechanical arm is equipped with a radar detector, which can quickly and accurately detect the ice layer, while the second mechanical arm can remove the floating snow on the ice surface through the purge fan to ensure the accuracy and reliability of the detection. It integrates multiple functional modules, including image acquisition, radar detection, purge and deformation force acquisition, etc., to ensure the accuracy of the detection data, realize the real-time collection of ice crack image data and echo amplitude data, and perform real-time analysis and judgment. The controller can timely detect the existence of ice cracks and assess the risk level, providing timely safety protection for cargo transportation on the ice surface.

[0122] In another preferred embodiment based on the above embodiment, refer to Figure 3 As shown, this embodiment provides an ice crack detection method, which is applied to the above-mentioned ice crack detection robot, including:

[0123] S100: Collecting detection path information, obtaining a total detection length, and determining a detection interval of the first robot arm according to the total detection length;

[0124] S200: Before detection, the acquisition device is controlled to acquire image data of the ice layer in front, and the image data is analyzed to obtain whether there is floating snow on the surface of the ice layer; when it is determined that there is floating snow on the surface of the ice layer, the floating snow area is obtained, and the second mechanical arm is controlled to blow the ice layer according to the floating snow area;

[0125] S300: after determining whether to purge the ice layer, controlling the first mechanical arm to detect the current position, collecting echo amplitude data, and determining whether there is an ice crack at the current position according to the echo amplitude data;

[0126] S400: When it is determined that there is an ice crack at the current position, the echo arrival time is collected and the pressure robot arm is controlled to apply pressure to the detection position, the deformation force of the ice layer is collected, and the risk level of the current position is obtained according to the echo amplitude data, the echo arrival time and the deformation force.

[0127] It is understandable that by using robots instead of manual labor to detect ice cracks, the work risks of personnel in harsh polar environments are effectively reduced, and the potential safety hazards caused by direct contact with the ice surface are avoided. The existence of the pressure manipulator arm enables the robot to apply pressure in time when ice cracks are found, collect the deformation force of the ice layer, realize the force analysis of the ice cracks, and help to fully understand the bearing capacity of the ice cracks. The robot automatically performs ice crack detection tasks, is not restricted by the polar environment, and can continue to work under harsh weather conditions, which improves the efficiency and coverage of ice crack detection. The first manipulator arm is equipped with a radar detector, which can quickly and accurately detect the ice layer, while the second manipulator arm can remove floating snow on the ice surface through a purge fan to ensure the accuracy and reliability of detection. It integrates multiple functional modules, including image acquisition, radar detection, purge and deformation force acquisition, etc., to ensure the accuracy of detection data, realize real-time collection of ice crack image data and echo amplitude data, and perform real-time analysis and judgment. The controller can promptly detect the existence of ice cracks and assess the risk level, providing timely safety protection for cargo transportation on the ice surface.

[0128] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0129] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An ice crack detection robot, characterized in that: include: case; A ski board, fixedly arranged below the housing, wherein at least one ski board is arranged; A collection device, fixedly arranged in front of the shell, and used for collecting image data in front of the detection robot; a first mechanical arm, a radar detector being arranged at the head thereof, the first mechanical arm being rotatably arranged above the shell, and the first mechanical arm being used for detecting ice layers; a second mechanical arm, wherein a blowing fan is disposed at the head thereof, the second mechanical arm is rotatably disposed above the housing and located at one side of the first mechanical arm, and the second mechanical arm is used for blowing away the ice layer; A pressure mechanical arm is arranged in front of the shell and is located on one side of the collection device, and is used to apply pressure to the detection position and collect the deformation force of the ice layer; A power device, fixedly arranged at the rear of the housing, and driving the robot to operate; A controller is fixedly disposed inside the housing and is electrically connected to the collection device, the first mechanical arm, the second mechanical arm, the pressure mechanical arm and the power device, respectively. The controller is used to: Collecting detection path information, obtaining a total detection length, and determining an interval time of detection by the first mechanical arm according to the total detection length; Before controlling the first robotic arm to perform detection, controlling the acquisition device to acquire image data of the ice layer in front, analyzing the image data to obtain whether there is floating snow on the surface of the ice layer; when it is determined that there is floating snow on the surface of the ice layer, obtaining the area of ​​floating snow, and controlling the second robotic arm to blow away the ice layer according to the area of ​​floating snow; After determining whether to purge the ice layer, controlling the first mechanical arm to detect the current position, collecting echo amplitude data, and determining whether there is an ice crack at the current position according to the echo amplitude data; When it is determined that there is an ice crack at the current position, the echo arrival time is collected and the pressure mechanical arm is controlled to apply pressure to the detection position, the deformation force of the ice layer is collected, and the risk level of the current position is obtained according to the echo amplitude data, the echo arrival time and the deformation force; When the controller determines the interval time of the first mechanical arm detection according to the total detection length, it includes: The controller compares the total detection length L with a first preset total detection length L1 and a second preset total detection length L2 respectively, L1<L2, and determines the detection interval time of the first robot arm according to the comparison result; When L≤L1, the controller determines that the detection interval of the first mechanical arm is a first preset interval T1; When L1<L≤L2, the controller determines that the detection interval of the first mechanical arm is a second preset interval T2; When L2<L, the controller determines that the detection interval of the first robot arm is a third preset interval T3; Among them, T1<T2<T3; After determining that the detection interval of the first mechanical arm is the i-th preset interval time Ti, i=1, 2, 3, the controller determines whether there is an ice crack at the current position according to the echo amplitude data, including: The controller compares the echo amplitude data F with a preset echo amplitude threshold Fmin, and determines whether there is an ice crack at the current position according to the comparison result; When F<Fmin, the controller determines that there is no ice crack at the current position, but there are ice cracks around the current position, and obtains the amplitude difference ΔF, ΔF=Fmin-F, and adjusts the detection interval Ti of the first manipulator according to the amplitude difference ΔF; When F=Fmin, the controller determines that there is no ice crack at the current position, and controls the first robotic arm to continue detecting at an interval time Ti; When F>Fmin, the controller determines that there is an ice crack at the current position, collects the echo arrival time Q, and determines the depth of the ice crack according to the echo arrival time Q; When the controller adjusts the detection interval Ti of the first robot arm according to the amplitude difference ΔF, it includes: The controller compares the amplitude difference ΔF with a first preset amplitude difference ΔF1 and a second preset amplitude difference ΔF2 respectively, ΔF1<ΔF2, and determines a time adjustment coefficient according to the comparison result to adjust the interval time Ti; When ΔF≤ΔF1, a first preset time adjustment coefficient A1 is determined to adjust the interval time Ti, and the operation continues with the adjusted interval time Ti*A1; When ΔF1<ΔF≤ΔF2, determine the second preset time adjustment coefficient A2 to adjust the interval time Ti, and continue to run with the adjusted interval time Ti*A2; When ΔF2<ΔF, determine the third preset time adjustment coefficient A3 to adjust the interval time Ti, and continue to run with the adjusted interval time Ti*A3; Among them, 0<A1<A2<A3<1.

2. The ice crack detection robot according to claim 1, characterized in that: When the controller analyzes the image data to obtain whether there is floating snow on the surface of the ice layer, it includes: Preprocessing the image data, wherein the preprocessing includes denoising, graying, and edge detection; Extracting texture information from the image, comparing the texture information with ice surface texture information, and determining whether there is floating snow on the ice surface based on the comparison result; When the texture information does not match the ice surface texture information, it is determined that floating snow exists on the surface of the ice layer, and the floating snow area M is obtained based on the edge detection.

3. The ice crack detection robot according to claim 2, characterized in that: When the controller controls the second mechanical arm to clear the ice layer according to the floating snow area, it includes: The controller compares the floating snow area M with the first preset floating snow area M1 and the second preset floating snow area M2 respectively, M1<M2, and determines the blowing speed of the second mechanical arm when blowing the ice layer according to the comparison result; When M≤M1, the controller determines that the blowing speed of the second mechanical arm when blowing the ice layer is the first preset speed S1; When M1<M≤M2, the controller determines that the blowing speed of the second mechanical arm when blowing the ice layer is a second preset speed S2; When M2<M, the controller determines that the blowing speed of the second mechanical arm when blowing the ice layer is a third preset speed S3; Among them, S1<S2<S3.

4. The ice crack detection robot according to claim 1, characterized in that: When the controller determines the ice crack depth according to the echo arrival time Q, it includes: The controller compares the echo arrival time Q with a first preset echo arrival time Q1 and a second preset echo arrival time Q2 respectively, Q1<Q2, and determines the ice crack depth according to the comparison result; When Q≤Q1, the controller determines that the ice crack depth is a first preset depth E1; When Q1<Q≤Q2, the controller determines that the ice crack depth is a second preset depth E2; When Q2<Q, the controller determines that the ice crack depth is a third preset depth E3; Among them, 0<E1<E2<E3.

5. The ice crack detection robot according to claim 4, characterized in that: When the controller obtains the risk level of the current position according to the echo amplitude data, the echo arrival time and the deformation force, it includes: The controller obtains an echo amplitude overflow value Fy, where Fy=F-Fmin, and compares the echo amplitude overflow value Fy with a first preset overflow value Fy1 and a second preset overflow value Fy2, respectively, where Fy1<Fy2, and determines the ice crack width according to the comparison result; When Fy≤Fy1, the controller determines that the ice crack width is a third preset width K3; When Fy1<Fy≤Fy2, the controller determines that the ice crack width is a second preset width K2; When Fy2<Fy, the controller determines that the ice crack width is a first preset width K1; Among them, 0<K1<K2<K3.

6. The ice crack detection robot according to claim 5, characterized in that: When the controller determines that the ice crack depth is the i-th preset depth Ei and the ice crack width is the n-th preset width Kn, i=1, 2, 3, n=1, 2, 3, the controller obtains the risk level of the current position according to the echo amplitude data, the echo arrival time and the deformation force, and further includes: The controller obtains the current position risk coefficient P according to the ice crack depth Ei, the ice crack width Kn and the deformation force N. The risk coefficient P is calculated by the following formula: P = Ei*a + Kn*bN*c; Among them, a, b, c represent weight coefficients, a+b+c=1; The controller compares the risk coefficient P with a first preset risk coefficient P1 and a second preset risk coefficient P2 respectively, P1<P2, and obtains the risk level of the current position according to the comparison result; When P≤P1, the risk level of the current location is determined to be the third preset risk level D3; When P1<P≤P2, the risk level of the current location is determined to be the second preset risk level D2; When P2<P, the risk level of the current location is determined to be the first preset risk level D1; The first preset risk level D1 indicates that the danger level of ice cracks is higher than that of the second preset risk level D2, and the second preset risk level D2 indicates that the danger level of ice cracks is higher than that of the third preset risk level D3.

7. An ice crack detection method, applied to the ice crack detection robot according to any one of claims 1 to 6, characterized in that: include: Collecting detection path information, obtaining a total detection length, and determining an interval time of detection by the first robotic arm according to the total detection length; Before detection, the acquisition device is controlled to acquire image data of the ice layer in front, and the image data is analyzed to obtain whether there is floating snow on the surface of the ice layer; when it is determined that there is floating snow on the surface of the ice layer, the floating snow area is obtained, and the second mechanical arm is controlled to blow the ice layer according to the floating snow area; After determining whether to purge the ice layer, controlling the first mechanical arm to detect the current position, collecting echo amplitude data, and determining whether there is an ice crack at the current position according to the echo amplitude data; When it is determined that there is an ice crack at the current position, the echo arrival time is collected and the pressure robot arm is controlled to apply pressure to the detection position to collect the deformation force of the ice layer. The risk level of the current position is obtained based on the echo amplitude data, the echo arrival time and the deformation force.

Images